Category Archives: image recognition

One-Pixel Attack Fools Neural Networks

Deep Neural Networks can be pretty good at identifying images — almost as good as they are at attracting Silicon Valley venture capital. But they can also be fairly brittle, and a slew of research projects over the last few years have been working on making the networks’ image classification less likely to be deliberately fooled.

One particular line of attack involves adding particularly-crafted noise to an image that flips some bits in the deep dark heart of the network, and makes it see something else where no human would notice the difference. We got tipped with a YouTube video …read more

Continue reading

Posted in artificial neural network, deep neural networks, hype, image recognition, software hacks, Uncategorized | Leave a comment

Google’s Inception Sees This Turtle as a Gun; Image Recognition Camouflage

The good people at MIT’s Computer Science and Artificial Intelligence Laboratory [CSAIL] have found a way of tricking Google’s InceptionV3 image classifier into seeing a rifle where there actually is a turtle. This is achieved by presenting the classifier with what is called ‘adversary examples’.

Adversary examples are a proven concept for 2D stills. In 2014 [Goodfellow], [Shlens] and [Szegedy] added imperceptible noise to the image of a panda that from then on was classified as gibbon. This method relies on the image being undisturbed and can be overcome by zooming, blurring or rotating the image.

The applicability for real …read more

Continue reading

Posted in 3d Printer hacks, ai, camouflage, computer vision, Google Inception, image recognition, inception, neural networks, news | Leave a comment

Hackaday Prize Entry: Automated Wildlife Recognition

Trail and wildlife cameras are commonly available nowadays, but the Wild Eye project aims to go beyond simply taking digital snapshots of critters. [Brenda Armour] uses a Raspberry Pi to not only take photos of wildlife who wander into the camera’s field of view, but to also automatically identify and categorize the animals seen using a visual recognition API from IBM via the Node-RED infrastructure. The result is a system that captures an image when motion is detected, sends the image to the visual recognition API, and attempts to identify any wildlife based on the returned data.

The visual recognition …read more

Continue reading

Posted in automation, camera, image recognition, motion, motion detection, node-red, node.js, opencv, Raspberry Pi, The Hackaday Prize, visual recognition, wildlife, wildlife camera | Leave a comment